import pandas as pd
import altair as alt

train_data = pd.read_csv('train.csv', index_col=0)
train_data

	MSSubClass	MSZoning	LotFrontage	LotArea	Street	Alley	LotShape	LandContour	Utilities	LotConfig	...	PoolArea	PoolQC	Fence	MiscFeature	MiscVal	MoSold	YrSold	SaleType	SaleCondition	SalePrice
Id
1	60	RL	65.0	8450	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	NaN	NaN	0	2	2008	WD	Normal	208500
2	20	RL	80.0	9600	Pave	NaN	Reg	Lvl	AllPub	FR2	...	0	NaN	NaN	NaN	0	5	2007	WD	Normal	181500
3	60	RL	68.0	11250	Pave	NaN	IR1	Lvl	AllPub	Inside	...	0	NaN	NaN	NaN	0	9	2008	WD	Normal	223500
4	70	RL	60.0	9550	Pave	NaN	IR1	Lvl	AllPub	Corner	...	0	NaN	NaN	NaN	0	2	2006	WD	Abnorml	140000
5	60	RL	84.0	14260	Pave	NaN	IR1	Lvl	AllPub	FR2	...	0	NaN	NaN	NaN	0	12	2008	WD	Normal	250000
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1456	60	RL	62.0	7917	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	NaN	NaN	0	8	2007	WD	Normal	175000
1457	20	RL	85.0	13175	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	MnPrv	NaN	0	2	2010	WD	Normal	210000
1458	70	RL	66.0	9042	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	GdPrv	Shed	2500	5	2010	WD	Normal	266500
1459	20	RL	68.0	9717	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	NaN	NaN	0	4	2010	WD	Normal	142125
1460	20	RL	75.0	9937	Pave	NaN	Reg	Lvl	AllPub	Inside	...	0	NaN	NaN	NaN	0	6	2008	WD	Normal	147500

1460 rows × 80 columns

X_train = train_data.drop(columns='SalePrice')

X_train.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1460 entries, 1 to 1460
Data columns (total 79 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   MSSubClass     1460 non-null   int64  
 1   MSZoning       1460 non-null   object 
 2   LotFrontage    1201 non-null   float64
 3   LotArea        1460 non-null   int64  
 4   Street         1460 non-null   object 
 5   Alley          91 non-null     object 
 6   LotShape       1460 non-null   object 
 7   LandContour    1460 non-null   object 
 8   Utilities      1460 non-null   object 
 9   LotConfig      1460 non-null   object 
 10  LandSlope      1460 non-null   object 
 11  Neighborhood   1460 non-null   object 
 12  Condition1     1460 non-null   object 
 13  Condition2     1460 non-null   object 
 14  BldgType       1460 non-null   object 
 15  HouseStyle     1460 non-null   object 
 16  OverallQual    1460 non-null   int64  
 17  OverallCond    1460 non-null   int64  
 18  YearBuilt      1460 non-null   int64  
 19  YearRemodAdd   1460 non-null   int64  
 20  RoofStyle      1460 non-null   object 
 21  RoofMatl       1460 non-null   object 
 22  Exterior1st    1460 non-null   object 
 23  Exterior2nd    1460 non-null   object 
 24  MasVnrType     1452 non-null   object 
 25  MasVnrArea     1452 non-null   float64
 26  ExterQual      1460 non-null   object 
 27  ExterCond      1460 non-null   object 
 28  Foundation     1460 non-null   object 
 29  BsmtQual       1423 non-null   object 
 30  BsmtCond       1423 non-null   object 
 31  BsmtExposure   1422 non-null   object 
 32  BsmtFinType1   1423 non-null   object 
 33  BsmtFinSF1     1460 non-null   int64  
 34  BsmtFinType2   1422 non-null   object 
 35  BsmtFinSF2     1460 non-null   int64  
 36  BsmtUnfSF      1460 non-null   int64  
 37  TotalBsmtSF    1460 non-null   int64  
 38  Heating        1460 non-null   object 
 39  HeatingQC      1460 non-null   object 
 40  CentralAir     1460 non-null   object 
 41  Electrical     1459 non-null   object 
 42  1stFlrSF       1460 non-null   int64  
 43  2ndFlrSF       1460 non-null   int64  
 44  LowQualFinSF   1460 non-null   int64  
 45  GrLivArea      1460 non-null   int64  
 46  BsmtFullBath   1460 non-null   int64  
 47  BsmtHalfBath   1460 non-null   int64  
 48  FullBath       1460 non-null   int64  
 49  HalfBath       1460 non-null   int64  
 50  BedroomAbvGr   1460 non-null   int64  
 51  KitchenAbvGr   1460 non-null   int64  
 52  KitchenQual    1460 non-null   object 
 53  TotRmsAbvGrd   1460 non-null   int64  
 54  Functional     1460 non-null   object 
 55  Fireplaces     1460 non-null   int64  
 56  FireplaceQu    770 non-null    object 
 57  GarageType     1379 non-null   object 
 58  GarageYrBlt    1379 non-null   float64
 59  GarageFinish   1379 non-null   object 
 60  GarageCars     1460 non-null   int64  
 61  GarageArea     1460 non-null   int64  
 62  GarageQual     1379 non-null   object 
 63  GarageCond     1379 non-null   object 
 64  PavedDrive     1460 non-null   object 
 65  WoodDeckSF     1460 non-null   int64  
 66  OpenPorchSF    1460 non-null   int64  
 67  EnclosedPorch  1460 non-null   int64  
 68  3SsnPorch      1460 non-null   int64  
 69  ScreenPorch    1460 non-null   int64  
 70  PoolArea       1460 non-null   int64  
 71  PoolQC         7 non-null      object 
 72  Fence          281 non-null    object 
 73  MiscFeature    54 non-null     object 
 74  MiscVal        1460 non-null   int64  
 75  MoSold         1460 non-null   int64  
 76  YrSold         1460 non-null   int64  
 77  SaleType       1460 non-null   object 
 78  SaleCondition  1460 non-null   object 
dtypes: float64(3), int64(33), object(43)
memory usage: 912.5+ KB

cat_cols = ['MSSubClass', 'MSZoning', 'Street', 'Alley', 'LotShape',
            'LandContour', 'Utilities', 'LotConfig', 'LandSlope', 'Neighborhood',
           'Condition1', 'Condition2', 'BldgType', 'HouseStyle', 'RoofStyle',
           'RoofMat1', 'Exterior1st', 'Exterior2nd', 'MasVnrType', 'Foundation',
           'Heating', 'Electrical', 'Fireplaces', 'GarageType', 'GarageFinish',
            'PavedDrive', 'MiscFeature']
num_cols = ['LotFrontage', 'LotArea', 'YearBuilt', 'YearRemodAdd', 'MasVnrArea',
           'BsmtFinSF1', 'BsmtFinSF1', 'BsmtUnfSF', 'TotalBsmtSF', '1stFlrSF', '2ndFlrSF',
           'LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath', 
           'HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'TotRmsAbvGrd', 'GarageYrBlt','GarageCars', 
           'GarageArea', 'WoodDeckSF', 'OpenPorchSF', 'EnclosedPorch', '3SsnPorch', 
            'ScreenPorch', 'PoolArea', 'MiscVal', 'MoSold', 'YrSold', ]
ord_cols = ['OverallQual', 'OverallCond', 'ExterQual', 'ExterCond', 'BsmtQual', 
           'BsmtCond','BsmtExposure', 'BsmtFinType1', 'BsmtFinType2', 'HeatingQC'
           'KitchenQual', 'Functional', 'FireplaceQu', 'GarageQual', 'GarageCond',
           'PoolQc', 'Fence', ]
bin_cols = ['CentralAir']

corr_df = (
    X_train
    .select_dtypes('number')
    .corr('spearman')
    .abs()                      # Use abs for negative correlation to stand out
    .stack()                    # Get df into long format for altair
    .reset_index(name='corr'))  # Name the index that is reset to avoid name collision

alt.Chart(corr_df).mark_circle().encode(
    x='level_0',
    y='level_1',
    size='corr',
    color='corr')

scatter_plot = alt.Chart(train_data).mark_point(size = 0.1).encode(
    alt.Y(alt.repeat('row'), type='quantitative'),
    alt.X(alt.repeat('column'), type='quantitative')
).properties(height = 100, width = 100
)

scatter_plot.repeat(column=num_cols[0:6], row=['SalePrice'])

scatter_plot.repeat(column=num_cols[6:12], row=['SalePrice'])

scatter_plot.repeat(column=num_cols[12:18], row=['SalePrice'])

scatter_plot.repeat(column=num_cols[18:24], row=['SalePrice'])

scatter_plot.repeat(column=num_cols[24:32], row=['SalePrice'])

Ordinal Categories

alt.Chart(train_data).mark_point(size = 0.1).encode(
    alt.Y(alt.repeat('row'), type='ordinal'),
    alt.X(alt.repeat('column'), type='ordinal')
).properties(height = 100, width = 100
).repeat(column=ord_cols, row=['SalePrice'])